iSTART is a game-based intelligent tutoring system (ITS) designed to improve students’ reading skills by providing training on reading comprehension strategies. Game-based practice in iSTART follows two main approaches: generative practice and identification practice. Generative practice games ask students to author self-explanations using one or more of the instructed strategies. Identification practice games require students to recognize or select appropriate strategies based on their analysis of example texts. This study explored the feasibility of implementing stealth assessments in iSTART using only an identification game. Specifically, this study examined the extent to which participants’ performance and attitudes related to a simple vocabulary game could predict the outcomes of standardized reading assessments. MTurk participants (N = 211) played identification games in iSTART and then rated their subjective gameplay experience. Participants also completed measures of their vocabulary and reading comprehension skills. Results indicated that participants’ performance in a vocabulary practice game was predictive of literacy skills. In addition, the possibility that students’ attitude towards the game moderated the relation between game performance and literacy skills was ruled out. These findings argue for the feasibility of implementing stealth assessment in simple games to facilitate the adaptivity of ITSs.